Disease-related compound identification based on deeping learning method

Abstract

Acute lung injury (ALI) is a serious respiratory disease, which can lead to acute respiratory failure or death. It is closely related to the pathogenesis of New Coronavirus pneumonia (COVID-19). Many researches showed that traditional Chinese medicine (TCM) had a good effect on its intervention, and network pharmacology could play a very important role. In order to construct "disease-gene-target-drug" interaction network more accurately, deep learning algorithm is utilized in this paper. Two ALI-related target genes (REAL and SATA3) are considered, and the active and inactive compounds of the two corresponding target genes are collected as training data, respectively. Molecular descriptors and molecular fingerprints are utilized to characterize each compound. Forest graph embedded deep feed forward network (forgeNet) is proposed to train. The experimental results show that forgeNet performs better than support vector machines (SVM), random forest (RF), logical regression (LR), Naive Bayes (NB), XGBoost, LightGBM and gcForest. forgeNet could identify 19 compounds in Erhuang decoction (EhD) and Dexamethasone (DXMS) more accurately.

Ursolic acid inhibits NF-κB signaling and attenuates MMP-9/TIMP-1 in progressive osteoarthritis: a network pharmacology-based analysis

“…26 The network strategy in the recent work is built on the "disease-gene-target-pathway-drug" interaction network, that characterizes the impact of drug on the disease network (targets/pathways). 65 The PPI network analysis predicted that 10 targets including IL-1b, STAT3, CASP3, PTGS2, IL-6, TNF-a, CCND1, BCL2L1, MMP-9, and VEGFA were the key targets of UA for the treatment of inammation. Among these key targets in the network, TNF-a and IL-1b are responsible for the activation of the NF-kB pathway by the production of pro-inammatory stimuli.…”

Exploring the action mechanism of Jinxin oral liquid on asthma by network pharmacology, molecular docking, and microRNA recognition

“…[77][78][79] Deep learning can also be applied for target identification and supplementation, disease-related component recognition, and screening potential natural products in some TCM studies integrating network pharmacology with machine learning. [80][81][82][83] Furthermore, our team intends to attempt using deep learning in additional research to investigate the efficacy and mechanism of JXOL in asthma, including the assessment of side effects, the prediction of new targets, the enhancement of JXOL composition, etc.…”

Construction of a neural network diagnostic model for renal fibrosis and investigation of immune infiltration characteristics

“…Least absolute shrinkage and selection operator (LASSO) logistic regression and support vector machine-recursive feature elimination (SVM-RFE), were used to identify predictive genes for renal fibrosis (11)(12)(13)(14)(15). The R package "glmnet" was used for LASSO analysis, and the optimal variable was found by the SVM-RFE algorithm.…”